{"id":"W4404792915","doi":"10.18653/v1/2024.emnlp-main.695","title":"The Mystery of the Pathological Path-star Task for Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"Strong; Government of Canada; Canadian Institute for Advanced Research","keywords":"Task (project management); Computer science; Path (computing); Star (game theory); Artificial intelligence; Natural language processing; Programming language; Engineering; Astrophysics; Physics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007482992,0.001282721,0.001886148,0.000522353,0.001529362,0.002726962,0.003325553,0.004195142,0.006319315],"category_scores_gemma":[0.04051762,0.00106661,0.001448785,0.0006598862,0.004600322,0.01360281,0.003578383,0.01140077,0.00262514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00140665,"about_ca_system_score_gemma":0.002239287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003347364,"about_ca_topic_score_gemma":0.004402261,"domain_scores_codex":[0.9957942,0.002496265,0.0001723797,0.0009614667,0.000385688,0.0001900311],"domain_scores_gemma":[0.970829,0.02287764,0.000675363,0.004162447,0.0007749473,0.000680622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006509951,0.0003082045,0.001979377,0.0007952985,0.0002297721,0.0003752288,0.00128887,0.1512057,0.003511077,0.6279968,0.06208297,0.1495757],"study_design_scores_gemma":[0.00005638301,0.00003861333,0.0001375355,0.00002904199,0.00001056973,0.00007606552,0.0000594748,0.2151077,0.0005374336,0.7809799,0.002946219,0.00002098459],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03276637,0.001184305,0.9335908,0.02155895,0.0003536453,0.00007616635,0.0007276565,0.002042478,0.007699662],"genre_scores_gemma":[0.6471804,0.001100341,0.3305512,0.00492835,0.001162531,0.000495748,0.002078488,0.001511627,0.01099135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007482992,"threshold_uncertainty_score":0.03957433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01562521754979921,"score_gpt":0.2726373696601032,"score_spread":0.257012152110304,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}